Hongbin Liu
Hongbin Liu
Ph.D. student, Duke University
Zweryfikowany adres z duke.edu - Strona główna
Cytowane przez
Cytowane przez
EncoderMI: Membership inference against pre-trained encoders in contrastive learning
H Liu, J Jia, W Qu, NZ Gong
Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications …, 2021
Pointguard: Provably robust 3d point cloud classification
H Liu, J Jia, NZ Gong
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021
StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning
Y Liu, J Jia, H Liu, NZ Gong
ACM Conference on Computer and Communications Security (CCS), 2022
PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning
H Liu, J Jia, NZ Gong
USENIX Security Symposium, 2022
Almost tight l0-norm certified robustness of top-k predictions against adversarial perturbations
J Jia, B Wang, X Cao, H Liu, NZ Gong
International Conference on Learning Representations (ICLR), 2022
Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning
X He, H Liu, NZ Gong, Y Zhang
European Conference on Computer Vision (ECCV), 2022
On the Intrinsic Differential Privacy of Bagging
H Liu, J Jia, NZ Gong
International Joint Conference on Artificial Intelligence (IJCAI), 2021
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
J Zhang, H Liu, J Jia, NZ Gong
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Visual Hallucinations of Multi-modal Large Language Models
W Huang, H Liu, M Guo, NZ Gong
Findings of the Association for Computational Linguistics (ACL), 2024
10 Security and Privacy Problems in Large Foundation Models
J Jia, H Liu, NZ Gong
AI Embedded Assurance for Cyber Systems, 2023
Pre-trained encoders in self-supervised learning improve secure and privacy-preserving supervised learning
H Liu, W Qu, J Jia, NZ Gong
IEEE Security and Privacy Workshops, 2024
PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees
J Zhang, J Jia, H Liu, NZ Gong
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models
H Liu, MK Reiter, NZ Gong
USENIX Security Symposium, 2024
Generation-based fuzzing? Don’t build a new generator, reuse!
C Pang, H Liu, Y Wang, NZ Gong, B Mao, J Xu
Computers & Security 129, 103178, 2023
Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models
H Liu, L Wang, O Thakkar, A Thakurta, A Narayanan
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–15